Related Experiment Video
Updated: Jun 12, 2026
06:07
Continuous Fluorescence-Based Endonuclease-Coupled DNA Methylation Assay to Screen for DNA Methyltransferase Inhibitors
Published on: August 5, 2022
A Neural Network-Enabled, Enzymatic cfDNA Methylation Assay for Colorectal Cancer Early Detection.
Manny D Bacolod1, Almudena Aguilera-Diaz1, Philip Feinberg1
1Weill Cornell Medicine New York, NY United States.
Cancer Prevention Research (Philadelphia, Pa.)
|June 11, 2026
Summary
A new non-invasive liquid biopsy test detects colorectal cancer (CRC) using cell-free DNA (cfDNA) methylation. This rapid, cost-effective assay shows high sensitivity and specificity, especially for early-stage CRC.
Area of Science:
- Oncology
- Molecular Diagnostics
- Bioinformatics
Background:
- Early detection of colorectal cancer (CRC) is crucial for survival but current noninvasive methods have limitations.
- Non-next-generation sequencing (non-NGS) liquid biopsy approaches offer potential for improved CRC screening.
- Cell-free DNA (cfDNA) methylation profiling is a promising biomarker for cancer detection.
Purpose of the Study:
- To develop and clinically evaluate a non-NGS liquid biopsy assay for CRC detection using cfDNA methylation.
- To assess the sensitivity and specificity of the assay, particularly for early-stage disease.
- To establish a rapid, cost-effective, and scalable screening tool for colorectal cancer.
Main Methods:
- Developed a non-NGS liquid biopsy assay targeting 40 CpG regions in cfDNA.
- Utilized a TET2-APOBEC enzymatic conversion method for cfDNA integrity and amplification.
- Employed quantitative polymerase chain reaction (qPCR) for methylation signal quantification and neural networks for predictive modeling.
- Evaluated the assay in 216 plasma samples (86 CRC cases, 130 controls).
Main Results:
- The assay demonstrated high performance in a validation cohort.
- A representative model achieved 92.3% sensitivity and 97.4% specificity.
- Notably, the model achieved 100% sensitivity for early-stage (Stage I/II) CRC.
- The assay is rapid, cost-effective, and scalable, utilizing qPCR and machine learning.
Conclusions:
- The developed cfDNA methylation assay shows significant potential as a practical, minimally invasive tool for CRC detection.
- The enzymatic conversion and machine learning-guided approach enhance assay efficiency and accuracy.
- Further validation in larger, prospective cohorts is necessary to confirm clinical utility and refine performance estimates, especially for early-stage CRC detection.
